An improved CNN model in image classification application on water turbidity DOI
Ying Nie, Yuqiang Chen, Jianlan Guo

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Сен. 27, 2024

Abstract Water turbidity is an important indicator for evaluating water clarity and plays role in environmental protection ecological balance. Due to the subtle changes images, differences captured are often too be classified. Convolutional neural networks (CNNs) widely used image classification perform well feature extraction classification. This study explored application of convolutional The innovation lies applying CNN focusing on optimizing model improve prediction accuracy efficiency. proposed four models based artificial intelligence, adjusted number layers accuracy. Experiments were conducted noise-free noisy datasets evaluate running time models. results show that CNN-10 with a dropout layer has 96.5% under conditions. opened up new applications fine-grained classification, further demonstrated effectiveness through experiments.

Язык: Английский

Growth rate comparison of three Kappaphycus alvarezii colour strains cultivated using tubular netting and tie-tie methods in the waters of Ecuador DOI Creative Commons
Lenin Cáceres-Farías, Milton Montúfar-Romero, César Lodeiros

и другие.

Journal of Applied Phycology, Год журнала: 2025, Номер unknown

Опубликована: Фев. 20, 2025

Язык: Английский

Процитировано

0
An improved CNN model in image classification application on water turbidity DOI Creative Commons
Ying Nie, Yuqiang Chen, Jianlan Guo

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 2, 2025

Язык: Английский

Процитировано

0
Macroalgas rojas: una alternativa ecológica para la agricultura sostenible del Ecuador. DOI Open Access

Angela Pacheco,

Estefany Lema Choez,

Jaime Naranjo-Morán

и другие.

Boletín de Investigaciones Marinas y Costeras, Год журнала: 2024, Номер 53(2), С. 143 - 168

Опубликована: Июль 2, 2024

El empleo de compuestos bioactivos extraídos macroalgas en forma formulaciones agrícolas representa una tecnología emergente con gran potencial para reducir la dependencia agroquímicos sintéticos. Al presente, los extractos algas marinas se consideranun recurso sostenible debido a su carácter biodegradable. En esta revisión discute reemplazar o variedad moléculas sintéticas cultivos económicamente importantes, tales como fertilizantes sintéticos nitrogenados y fosfatados, reguladores del crecimiento hormonales plaguicidas organoclorados organofosforados. Por presencia extensa gamade sustancias bioactivas ya registradas ciertas prevén buenos candidatos producción bioformulaciones vegetales.En este sentido, el aprovechamiento comercial biotecnológico las podría beneficiar economía local. Sin embargo, pesea todo existe muy poca información contenido metabolómico químico total. Esta bibliográficaresume que propone uso Kappaphycus. alvarezii, Acanthophora spicifera e Hypnea spinella dentro delsector agrícola ecuatoriano alternativa reducción pesticidas.

Процитировано

0
An improved CNN model in image classification application on water turbidity DOI
Ying Nie, Yuqiang Chen, Jianlan Guo

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Сен. 27, 2024

Abstract Water turbidity is an important indicator for evaluating water clarity and plays role in environmental protection ecological balance. Due to the subtle changes images, differences captured are often too be classified. Convolutional neural networks (CNNs) widely used image classification perform well feature extraction classification. This study explored application of convolutional The innovation lies applying CNN focusing on optimizing model improve prediction accuracy efficiency. proposed four models based artificial intelligence, adjusted number layers accuracy. Experiments were conducted noise-free noisy datasets evaluate running time models. results show that CNN-10 with a dropout layer has 96.5% under conditions. opened up new applications fine-grained classification, further demonstrated effectiveness through experiments.

Язык: Английский

Процитировано

0